Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/cookys/autopilotnpx agentmods add skills/cookys/autopilot/research-to-shipWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cookys/autopilot/research-to-ship)<a href="https://agentmods.dev/skills/cookys/autopilot/research-to-ship"><img src="https://agentmods.dev/badge/skills/cookys/autopilot/research-to-ship/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cookys/autopilot/research-to-ship"><img src="https://agentmods.dev/badge/skills/cookys/autopilot/research-to-ship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00168 | $0.01872 |
| Opus 5 | $0.00084 | $0.00936 |
| Sonnet 5 | $0.00034 | $0.00374 |
| Haiku 4.5 | $0.00017 | $0.00187 |
Grade B, and why
research-to-ship scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
!`cat .claude/dispatch-config.md 2>/dev/null || true` How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
research-to-ship — a topic → researched, reviewed, shipped
Routing overlap? If this intent better matches a sibling skill, redirect per references/routing-tiebreaks.md (prefer human-gated pipelines over full autonomy).
A pinned chain that fixes the sequence and the human gates; the real work is delegated to existing autopilot skills. It exists because that exact sequence (best-practice research → plan → bounded plan-readiness gate → project → dev-flow) is a recurring ritual worth one command instead of re-typing each time.
Dispatch Chains (auto-injected)
!cat .claude/dispatch-config.md 2>/dev/null || true
Input — the topic
The objective/topic is whatever the user passed after the command. If it is empty, ask for it in one
line before starting. Derive a kebab-case <slug> from it for the plan/project filenames.
The pipeline (Phase 0 optional, then 5 phases, a human gate between each)
Run the phases in order. At each gate, use AskUserQuestion and do not proceed until the user
approves — this is what keeps the flow participatory (the opposite of ceo-agent's full autonomy).
Phase 0 — (optional) discover the design · delegate → autopilot:brainstorm
Only when the topic starts fuzzy — the options don't exist yet. If the user hands a vague need
("not sure how to approach X / 還沒想清楚"), run autopilot:brainstorm first: Socratic exploration →
2-3 approaches → a design spec the user approves. Then carry the chosen approach into Phase 1. Skip
Phase 0 when the topic is already a clear question (most invocations) — go straight to Phase 1.
Gate (only if Phase 0 ran): "design approved — research best-practice for it?"
Phase 1 — Research best-practice · delegate → autopilot:survey
Invoke autopilot:survey on the topic for external best-practice (dual researcher + skeptic). If the
topic needs deep, multi-source, fact-checked synthesis, use deep-research instead.
Gate: present the synthesized findings → "research enough to plan, or dig deeper / redirect?"
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago Changed · +2 lines a2c042736495
- 10d ago First seen · 111 lines · 168 tokens per session scan B 6f0814576c96
research-to-ship is a skill published in the GitHub repository cookys/autopilot (11 stars, last pushed today), licensed MIT. It adds 168 tokens to every session and 1,872 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…